© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 26255
    Prev
    Next
    INDEX
    Explanations

    told to, heard that, wondering what

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åħ¬åı·
    -0.09
    åİŁåĪĽæĸĩç«ł
    -0.09
    undy
    -0.09
    ÙĪاÙĨÙĬ
    -0.08
    èĢĮæĹł
    -0.07
    说罢
    -0.07
    大ä¸įäºĨ
    -0.07
    æľ¬åĬŀæ³ķ
    -0.07
    åħļçļĦäºĮåįģ大
    -0.07
    رائ
    -0.07
    POSITIVE LOGITS
    ç»Ļå®Ŀå®Ŀ
    0.08
    å§IJ妹
    0.08
    å®Ŀå¦Ī
    0.07
    ä¸Ģ缴éĥ½
    0.07
    æĪĸèĢħæĺ¯
    0.07
     nen
    0.07
    çļĦåIJ§
    0.07
    BB
    0.07
    å®Ŀå®Ŀ
    0.07
    åºĶ该注æĦı
    0.07
    Activations Density 0.018%

    No Known Activations